© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 429
    Prev
    Next
    INDEX
    Explanations

    instances of the word "keep" and its forms, sometimes followed by the definite article.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]();
    -0.69
     McCullough
    -0.69
     jSON
    -0.68
    queryInterface
    -0.66
    writeFieldEnd
    -0.65
    ="@+
    -0.64
     Happening
    -0.64
    iddhar
    -0.63
     AspNetCore
    -0.63
    yadh
    -0.63
    POSITIVE LOGITS
     kept
    1.84
     keep
    1.84
    keeping
    1.82
     keeping
    1.80
    keep
    1.77
     keeps
    1.75
     Keeping
    1.73
     Keep
    1.71
     maintained
    1.71
     maintain
    1.70
    Activations Density 2.763%

    No Known Activations